paper-with-me

Papers

External Knowledge Selection with Weighted Negative Sampling in Knowledge-grounded Task-oriented Dialogue Systems

2022-09-06 · Janghoon Han, Joongbo Shin, Hosung Song, Hyunjik Jo, Gyeonghun Kim, Yireun Kim, Stanley Jungkyu Choi

Constructing a robust dialogue system on spoken conversations bring more challenge than written conversation. In this respect, DSTC10-Track2-Task2 is proposed, which aims to build a task-oriented dialogue (TOD) system incorporating unstructured external knowledge on a spoken conversation, extending DSTC9-Track1. This paper introduces our system containing four advanced methods: data construction, weighted negative sampling, post-training, and style transfer. We first automatically construct a large training data because DSTC10-Track2 does not release the official training set. For the knowledge selection task, we propose weighted negative sampling to train the model more fine-grained manner. We also employ post-training and style transfer for the response generation task to generate an appropriate response with a similar style to the target response. In the experiment, we investigate the effect of weighted negative sampling, post-training, and style transfer. Our model ranked 7 out of 16 teams in the objective evaluation and 6 in human evaluation.

📄 PDF Abstract BibTeX arXiv:2209.02251

Code (1)

hanjanghoon/Weighted_NS 공식 구현 pytorch

Tasks

Response GenerationStyle TransferTask-Oriented Dialogue Systems

Similar Papers 제목 키워드 기반

Learning to Select External Knowledge with Multi-Scale Negative Sampling

2021-02-03 · Huang He, Hua Lu, Siqi Bao, Fan Wang 외

The Track-1 of DSTC9 aims to effectively answer user requests or questions during task-oriented dialogues, which are out of the scope of APIs/DB. By leveraging external knowledge resources, relevant information can be re…

Response Generation

word2vec Skip-Gram with Negative Sampling is a Weighted Logistic PCA

2017-05-27 · Andrew J. Landgraf, Jeremy Bellay

We show that the skip-gram formulation of word2vec trained with negative sampling is equivalent to a weighted logistic PCA. This connection allows us to better understand the objective, compare it to other word embedding…

Reward-Weighted Sampling: Enhancing Non-Autoregressive Characteristics in Masked Diffusion LLMs

2025-08-31 · Daehoon Gwak, Minseo Jung, Junwoo Park, Minho Park 외 arxiv

Masked diffusion models (MDMs) offer a promising non-autoregressive alternative for large language modeling. Standard decoding methods for MDMs, such as confidence-based sampling, select tokens independently based on ind…

Neighborhood-based Hard Negative Mining for Sequential Recommendation

2023-06-12 · Lu Fan, Jiashu Pu, Rongsheng Zhang, Xiao-Ming Wu

Negative sampling plays a crucial role in training successful sequential recommendation models. Instead of merely employing random negative sample selection, numerous strategies have been proposed to mine informative neg…

Sequential Recommendation

KnowPO: Knowledge-aware Preference Optimization for Controllable Knowledge Selection in Retrieval-Augmented Language Models

2024-08-06 · Ruizhe Zhang, Yongxin Xu, Yuzhen Xiao, Runchuan Zhu 외

By integrating external knowledge, Retrieval-Augmented Generation (RAG) has become an effective strategy for mitigating the hallucination problems that large language models (LLMs) encounter when dealing with knowledge-i…

HallucinationRAGRetrievalRetrieval-augmented Generation